Skip to content

[feat] mrotary embedding qknorm fused code#1427

Merged
xytpai merged 4 commits intoROCm:xyt/qknorm_mropefrom
amd-youchen:feature-add-qknorm-rope-fused
Nov 19, 2025
Merged

[feat] mrotary embedding qknorm fused code#1427
xytpai merged 4 commits intoROCm:xyt/qknorm_mropefrom
amd-youchen:feature-add-qknorm-rope-fused

Conversation

@amd-youchen
Copy link

Motivation

Technical Details

Test Plan

Test Result

Submission Checklist

@xytpai xytpai merged commit 152e6cc into ROCm:xyt/qknorm_mrope Nov 19, 2025
xytpai added a commit that referenced this pull request Nov 20, 2025
* add fused mrope rms

* add op_tests/test_fused_mrope_rms.py

* fix build errors

* fix bugs

* using load instead of nontemporal_load

* fix lint

* fix lint2

* fix lint2

* refine code

* [feat] mrotary embedding qknorm fused code (#1427)

* add two

* fix type error

* add extra assert

* add v as ret

* fix lint

---------

Co-authored-by: Xin Huang <Xin.Huang@amd.com>
Co-authored-by: ChenYou <youchen@amd.com>
xytpai added a commit to xytpai/aiter that referenced this pull request Nov 20, 2025
* add fused mrope rms

* add op_tests/test_fused_mrope_rms.py

* fix build errors

* fix bugs

* using load instead of nontemporal_load

* fix lint

* fix lint2

* fix lint2

* refine code

* [feat] mrotary embedding qknorm fused code (ROCm#1427)

* add two

* fix type error

* add extra assert

* add v as ret

* fix lint

---------

Co-authored-by: Xin Huang <Xin.Huang@amd.com>
Co-authored-by: ChenYou <youchen@amd.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants